█

AI/TLDR

DeepSeek · 2026-10-17 · major

DeepSeek Search and Fetch API — web search for agents at $0.75 per 1,000 calls

DeepSeek opened its in-house search engine to developers as two API endpoints: Search returns ranked web results and Fetch turns one page into Markdown. Each costs $0.75 per 1,000 successful requests, with a 5 QPS limit.

DeepSeek API docs social card with the DeepSeek whale logo

DeepSeek now sells the web search behind its own chat app as a plain API for agents and RAG apps.

Quick facts

MakerDeepSeek
Endpoints/v1/tools/search, /v1/tools/fetch
Price$0.75 per 1,000 successful requests (each API)
Rate limit5 QPS per account, per API
Results per search1–50 (default 10)
LaunchedOctober 17, 2026

Pricing

Search$0.75 / 1,000 successful requests
Fetch$0.75 / 1,000 successful requests
Via DeepSeek Harness, Claude Code or Codex · server-side tool calls free until Nov 1, 2026$0
source ↗

What is it?

The DeepSeek Search and Fetch API, opened on October 17, 2026, gives developers the same in-house search engine that powers DeepSeek's web and API search. Search takes a query and returns up to 50 ranked results with titles, snippets, longer model-oriented summaries and, on request, full page content. Fetch takes one URL and returns the page as Markdown.

How does it work?

Both are JSON endpoints under api.deepseek.com/v1/tools that use a normal DeepSeek API key. Queries accept operators such as site:, lang:, after: and before:, and every result carries a rerank_score from 0 to 3 and an authority tier from 0 to 4 so an agent can drop weak sources. DeepSeek's changelog says the engine indexes hundreds of billions of pages and filters SEO spam and low-quality AI-generated content.

Why does it matter?

Agents and RAG apps need fresh web data, and this gives DeepSeek users a search tool from the same vendor and on the same bill as the model. Billing counts only successful calls: empty results, failures and timeouts are free. Server-side tool calls made through DeepSeek Harness, Claude Code or Codex stay free until November 1, 2026.

Who is it for?

developers building agents and RAG apps

Frequently asked questions

Which DeepSeek Search API calls are billed?
DeepSeek bills its Search and Fetch API only for HTTP 200 responses that return a result. A search must return a non-empty results list and a fetch must return page content. Failed requests, empty results and timeouts are not billed, and the count parameter does not change the $0.75 per 1,000 price.
Is DeepSeek web search free in Claude Code or Codex?
DeepSeek says server-side Search and Fetch tool calls made through DeepSeek Harness, Claude Code or Codex are currently free. Per-request billing for those calls starts at 00:00 Beijing time on November 1, 2026. Direct calls to the Search and Fetch endpoints are billed at $0.75 per 1,000 successful requests.
What are the rate limits of the DeepSeek Search and Fetch API?
DeepSeek Search and Fetch each allow 5 requests per second per account, no matter how many API keys the account has. The two limits are separate from each other and from model concurrency limits. Fetch also has a per-domain limit, and any request over a limit gets HTTP 429 and should be retried after a wait.
Can the DeepSeek Search API filter by site, language or date?
Yes. DeepSeek Search queries accept site: and -site: to include or exclude domains, lang: with comma-separated language codes, after: and before: for publication dates, quoted exact phrases and minus terms. Each result also returns a publication date when known, a rerank_score from 0 to 3 and an authority tier from 0 to 4.

Try it

POST https://api.deepseek.com/v1/tools/search with {"query": "...", "count": 5}

Sources · 2 outlets

Tags

  • deepseek
  • web-search
  • search-api
  • fetch
  • agents
  • rag
  • api
  • pricing
  • show-hn

← All releases · Learn AI